nucleusai_nucleus-22b-token-500b needs about 22.4 GB of memory at Q4_K_M (a 13.2 GB file) with an 8K context window, so it fits on a 24 GB GPU. This repository has 12 quants, from 9.1 GB (Q2_K) to 23.2 GB (Q8_0).
Nucleus-22B-token-500B: 21.8B parameter causal decoder-only model
Nucleus-22B-token-500B is a 21.8B parameter causal decoder-only model trained on 500B tokens of RefinedWeb and curated corpora. It is released under the MIT license and supports English text generation. The model is available in multiple GGUF quantisations for llama.cpp and compatible clients.
Good at
- Large context generation
- High token throughput
- English language tasks
Limits
- No vision support
- English only
- Requires fine‑tuning for production use
Best for
- Research on large language models
- Foundation for fine‑tuning
- Text generation and summarization
Who it’s for. Researchers and developers who need a large open‑source language model for experimentation or as a base for further fine‑tuning. The model is suitable for academic projects and prototyping but should not be used in production without risk assessment.
Quants & memory
| Quant | File | Est. memory | vs VRAM | Result | |
|---|---|---|---|---|---|
| Q2_K | 9.1 GB | 11.8 GB | Too big | Get file → | |
| Q3_K_S | 9.5 GB | 12.1 GB | Too big | Get file → | |
| Q3_K_M | 10.6 GB | 13.3 GB | Too big | Get file → | |
| Q3_K_L | 11.6 GB | 14.3 GB | Too big | Get file → | |
| Q4_0 | 12.3 GB | 15.0 GB | Too big | Get file → | |
| Q4_K_S | 12.4 GB | 15.1 GB | Too big | Get file → | |
| Q4_K_M | 13.2 GB | 15.9 GB | Too big | Get file → | |
| Q5_0 | 15.0 GB | 17.7 GB | Too big | Get file → | |
| Q5_K_S | 15.0 GB | 17.7 GB | Too big | Get file → | |
| Q5_K_M | 15.5 GB | 18.2 GB | Too big | Get file → | |
| Q6_K | 17.9 GB | 20.6 GB | Too big | Get file → | |
| Q8_0 | 23.2 GB | 25.9 GB | Too big | Get file → |
For 8 GB VRAM use Q4_K or Q4_K_S (file size 12.34 GB, 21.6 GB memory at 8k context). For 12 GB VRAM use Q5_K_M (15.47 GB, 24.7 GB memory). For 16 GB VRAM use Q6_K (17.91 GB, 27.1 GB memory).
What GPU do you need for nucleusai_nucleus-22b-token-500b?
These figures add the file size, an fp16 KV cache at an 8K context window (worked out from this model’s own header) and about 0.5 GB for the runtime. They are estimates, so leave a little headroom, and expect to use less context or a smaller quant if you are right at the limit.
- 4 GB VRAM: no quant fits at an 8K context.
- 6 GB VRAM: no quant fits at an 8K context.
- 8 GB VRAM: no quant fits at an 8K context.
- 12 GB VRAM: no quant fits at an 8K context.
- 16 GB VRAM: no quant fits at an 8K context.
- 24 GB VRAM: the best quant that fits is Q4_K_M (13.2 GB file, about 22.4 GB in use).
- 32 GB VRAM: the best quant that fits is Q6_K (17.9 GB file, about 27.1 GB in use).
- 48 GB VRAM: the best quant that fits is Q8_0 (23.2 GB file, about 32.4 GB in use).
Which nucleusai_nucleus-22b-token-500b quant should you choose?
Q4_K_M is the usual starting point for nucleusai_nucleus-22b-token-500b: it balances file size and quality well. Here it is a 13.2 GB file.
The Q8_0 file is 23.2 GB, about 1.8 times the size of Q4_K_M. It keeps the weights closer to the original, which only matters if you have the memory to spare.
If memory is tight, the smallest file is Q2_K at 9.1 GB, with the quality trade-offs that come with fewer bits. Use it only when memory is very tight. Expect a clear drop in quality, which is usually worse on small models and easier to live with on large ones.
New to quant names? Read GGUF quantization explained.
Specifications
Architecture from the GGUF header
Source
Frequently asked questions about nucleusai_nucleus-22b-token-500b
How much VRAM does nucleusai_nucleus-22b-token-500b need?
About 22.4 GB at Q4_K_M with an 8K context window. That is the 13.2 GB file, plus the KV cache and roughly 0.5 GB of runtime overhead. Smaller quants need less and longer context needs more.
Can I run nucleusai_nucleus-22b-token-500b on an 8 GB GPU?
Not at an 8K context. The smallest file needs about 18.3 GB, so you would need a larger GPU or CPU offloading.
What is the file size of nucleusai_nucleus-22b-token-500b GGUF?
It depends on the quant: Q2_K is 9.1 GB, Q3_K_S is 9.5 GB, Q3_K_M is 10.6 GB, Q3_K_L is 11.6 GB, Q4_0 is 12.3 GB, Q4_K_S is 12.4 GB and 6 more.
What context length does nucleusai_nucleus-22b-token-500b support?
The GGUF header lists a trained context length of 2,048 tokens (2K). The KV cache grows with the context you use: about 8.7 GB at 8K and 2.2 GB at 2K.
Where can I download nucleusai_nucleus-22b-token-500b GGUF?
The files are on Hugging Face in the TheBloke/nucleus-22B-token-500B-GGUF repository. The download buttons on this page open the file on Hugging Face. ggufmodels.com does not host any model files.
What license does nucleusai_nucleus-22b-token-500b use?
Hugging Face lists the license as mit. Licenses can differ between the quantized files and the original model, so check the repository and the base model before commercial use.
Can I run Nucleus-22B-token-500B on 8 GB VRAM?
Use the Q4_K or Q4_K_S quantised model; it requires about 21.6 GB memory at 8k context, so 8 GB VRAM is insufficient.
Is the model multilingual?
The model is trained on English data only and does not generalise well to other languages.
What license does the model use?
The model is released under the MIT license.